pcap-linux.c

用来监视网络通信数据的源代码和应用程序,方便网络程序底层开发.

		if (handle->break_loop) {
			/*
			 * Yes - clear the flag that indicates that it
			 * has, and return -2 as an indication that we
			 * were told to break out of the loop.
			 */
			handle->break_loop = 0;
			return -2;
		}
		fromlen = sizeof(from);
		packet_len = recvfrom(
			handle->fd, bp + offset,
			handle->bufsize - offset, MSG_TRUNC,
			(struct sockaddr *) &from, &fromlen);
	} while (packet_len == -1 && errno == EINTR);

	/* Check if an error occured */

	if (packet_len == -1) {
		if (errno == EAGAIN)
			return 0;	/* no packet there */
		else {
			snprintf(handle->errbuf, sizeof(handle->errbuf),
				 "recvfrom: %s", pcap_strerror(errno));
			return -1;
		}
	}

#ifdef HAVE_PF_PACKET_SOCKETS
	/*
	 * If this is from the loopback device, reject outgoing packets;
	 * we'll see the packet as an incoming packet as well, and
	 * we don't want to see it twice.
	 *
	 * We can only do this if we're using PF_PACKET; the address
	 * returned for SOCK_PACKET is a "sockaddr_pkt" which lacks
	 * the relevant packet type information.
	 */
	if (!handle->md.sock_packet &&
	    from.sll_ifindex == handle->md.lo_ifindex &&
	    from.sll_pkttype == PACKET_OUTGOING)
		return 0;
#endif

#ifdef HAVE_PF_PACKET_SOCKETS
	/*
	 * If this is a cooked device, fill in the fake packet header.
	 */
	if (handle->md.cooked) {
		/*
		 * Add the length of the fake header to the length
		 * of packet data we read.
		 */
		packet_len += SLL_HDR_LEN;

		hdrp = (struct sll_header *)bp;

		/*
		 * Map the PACKET_ value to a LINUX_SLL_ value; we
		 * want the same numerical value to be used in
		 * the link-layer header even if the numerical values
		 * for the PACKET_ #defines change, so that programs
		 * that look at the packet type field will always be
		 * able to handle DLT_LINUX_SLL captures.
		 */
		switch (from.sll_pkttype) {

		case PACKET_HOST:
			hdrp->sll_pkttype = htons(LINUX_SLL_HOST);
			break;

		case PACKET_BROADCAST:
			hdrp->sll_pkttype = htons(LINUX_SLL_BROADCAST);
			break;

		case PACKET_MULTICAST:
			hdrp->sll_pkttype = htons(LINUX_SLL_MULTICAST);
			break;

		case PACKET_OTHERHOST:
			hdrp->sll_pkttype = htons(LINUX_SLL_OTHERHOST);
			break;

		case PACKET_OUTGOING:
			hdrp->sll_pkttype = htons(LINUX_SLL_OUTGOING);
			break;

		default:
			hdrp->sll_pkttype = -1;
			break;
		}

		hdrp->sll_hatype = htons(from.sll_hatype);
		hdrp->sll_halen = htons(from.sll_halen);
		memcpy(hdrp->sll_addr, from.sll_addr,
		    (from.sll_halen > SLL_ADDRLEN) ?
		      SLL_ADDRLEN :
		      from.sll_halen);
		hdrp->sll_protocol = from.sll_protocol;
	}
#endif

	/*
	 * XXX: According to the kernel source we should get the real
	 * packet len if calling recvfrom with MSG_TRUNC set. It does
	 * not seem to work here :(, but it is supported by this code
	 * anyway.
	 * To be honest the code RELIES on that feature so this is really
	 * broken with 2.2.x kernels.
	 * I spend a day to figure out what's going on and I found out
	 * that the following is happening:
	 *
	 * The packet comes from a random interface and the packet_rcv
	 * hook is called with a clone of the packet. That code inserts
	 * the packet into the receive queue of the packet socket.
	 * If a filter is attached to that socket that filter is run
	 * first - and there lies the problem. The default filter always
	 * cuts the packet at the snaplen:
	 *
	 * # tcpdump -d
	 * (000) ret      #68
	 *
	 * So the packet filter cuts down the packet. The recvfrom call
	 * says "hey, it's only 68 bytes, it fits into the buffer" with
	 * the result that we don't get the real packet length. This
	 * is valid at least until kernel 2.2.17pre6.
	 *
	 * We currently handle this by making a copy of the filter
	 * program, fixing all "ret" instructions with non-zero
	 * operands to have an operand of 65535 so that the filter
	 * doesn't truncate the packet, and supplying that modified
	 * filter to the kernel.
	 */

	caplen = packet_len;
	if (caplen > handle->snapshot)
		caplen = handle->snapshot;

	/* Run the packet filter if not using kernel filter */
	if (!handle->md.use_bpf && handle->fcode.bf_insns) {
		if (bpf_filter(handle->fcode.bf_insns, bp,
		                packet_len, caplen) == 0)
		{
			/* rejected by filter */
			return 0;
		}
	}

	/* Fill in our own header data */

	if (ioctl(handle->fd, SIOCGSTAMP, &pcap_header.ts) == -1) {
		snprintf(handle->errbuf, sizeof(handle->errbuf),
			 "ioctl: %s", pcap_strerror(errno));
		return -1;
	}
	pcap_header.caplen	= caplen;
	pcap_header.len		= packet_len;

	/*
	 * Count the packet.
	 *
	 * Arguably, we should count them before we check the filter,
	 * as on many other platforms "ps_recv" counts packets
	 * handed to the filter rather than packets that passed
	 * the filter, but if filtering is done in the kernel, we
	 * can't get a count of packets that passed the filter,
	 * and that would mean the meaning of "ps_recv" wouldn't
	 * be the same on all Linux systems.
	 *
	 * XXX - it's not the same on all systems in any case;
	 * ideally, we should have a "get the statistics" call
	 * that supplies more counts and indicates which of them
	 * it supplies, so that we supply a count of packets
	 * handed to the filter only on platforms where that
	 * information is available.
	 *
	 * We count them here even if we can get the packet count
	 * from the kernel, as we can only determine at run time
	 * whether we'll be able to get it from the kernel (if
	 * HAVE_TPACKET_STATS isn't defined, we can't get it from
	 * the kernel, but if it is defined, the library might
	 * have been built with a 2.4 or later kernel, but we
	 * might be running on a 2.2[.x] kernel without Alexey
	 * Kuznetzov's turbopacket patches, and thus the kernel
	 * might not be able to supply those statistics).  We
	 * could, I guess, try, when opening the socket, to get
	 * the statistics, and if we can not increment the count
	 * here, but it's not clear that always incrementing
	 * the count is more expensive than always testing a flag
	 * in memory.
	 */
	handle->md.stat.ps_recv++;

	/* Call the user supplied callback function */
	callback(userdata, &pcap_header, bp);

	return 1;
}

/*
 *  Get the statistics for the given packet capture handle.
 *  Reports the number of dropped packets iff the kernel supports
 *  the PACKET_STATISTICS "getsockopt()" argument (2.4 and later
 *  kernels, and 2.2[.x] kernels with Alexey Kuznetzov's turbopacket
 *  patches); otherwise, that information isn't available, and we lie
 *  and report 0 as the count of dropped packets.
 */
static int
pcap_stats_linux(pcap_t *handle, struct pcap_stat *stats)
{
#ifdef HAVE_TPACKET_STATS
	struct tpacket_stats kstats;
	socklen_t len = sizeof (struct tpacket_stats);
#endif

#ifdef HAVE_TPACKET_STATS
	/*
	 * Try to get the packet counts from the kernel.
	 */
	if (getsockopt(handle->fd, SOL_PACKET, PACKET_STATISTICS,
			&kstats, &len) > -1) {
		/*
		 * In "linux/net/packet/af_packet.c", at least in the
		 * 2.4.9 kernel, "tp_packets" is incremented for every
		 * packet that passes the packet filter *and* is
		 * successfully queued on the socket; "tp_drops" is
		 * incremented for every packet dropped because there's
		 * not enough free space in the socket buffer.
		 *
		 * When the statistics are returned for a PACKET_STATISTICS
		 * "getsockopt()" call, "tp_drops" is added to "tp_packets",
		 * so that "tp_packets" counts all packets handed to
		 * the PF_PACKET socket, including packets dropped because
		 * there wasn't room on the socket buffer - but not
		 * including packets that didn't pass the filter.
		 *
		 * In the BSD BPF, the count of received packets is
		 * incremented for every packet handed to BPF, regardless
		 * of whether it passed the filter.
		 *
		 * We can't make "pcap_stats()" work the same on both
		 * platforms, but the best approximation is to return
		 * "tp_packets" as the count of packets and "tp_drops"
		 * as the count of drops.
		 */
		handle->md.stat.ps_recv = kstats.tp_packets;
		handle->md.stat.ps_drop = kstats.tp_drops;
	}
	else
	{
		/*
		 * If the error was EOPNOTSUPP, fall through, so that
		 * if you build the library on a system with
		 * "struct tpacket_stats" and run it on a system
		 * that doesn't, it works as it does if the library
		 * is built on a system without "struct tpacket_stats".
		 */
		if (errno != EOPNOTSUPP) {
			snprintf(handle->errbuf, PCAP_ERRBUF_SIZE,
			    "pcap_stats: %s", pcap_strerror(errno));
			return -1;
		}
	}
#endif
	/*
	 * On systems where the PACKET_STATISTICS "getsockopt()" argument
	 * is supported on PF_PACKET sockets:
	 *
	 *	"ps_recv" counts only packets that *passed* the filter,
	 *	not packets that didn't pass the filter.  This includes
	 *	packets later dropped because we ran out of buffer space.
	 *
	 *	"ps_drop" counts packets dropped because we ran out of
	 *	buffer space.  It doesn't count packets dropped by the
	 *	interface driver.  It counts only packets that passed
	 *	the filter.
	 *
	 *	Both statistics include packets not yet read from the
	 *	kernel by libpcap, and thus not yet seen by the application.
	 *
	 * On systems where the PACKET_STATISTICS "getsockopt()" argument
	 * is not supported on PF_PACKET sockets:
	 *
	 *	"ps_recv" counts only packets that *passed* the filter,
	 *	not packets that didn't pass the filter.  It does not
	 *	count packets dropped because we ran out of buffer
	 *	space.
	 *
	 *	"ps_drop" is not supported.
	 *
	 *	"ps_recv" doesn't include packets not yet read from
	 *	the kernel by libpcap.
	 */
	*stats = handle->md.stat;
	return 0;
}

/*
 * Description string for the "any" device.
 */
static const char any_descr[] = "Pseudo-device that captures on all interfaces";

int
pcap_platform_finddevs(pcap_if_t **alldevsp, char *errbuf)
{
	if (pcap_add_if(alldevsp, "any", 0, any_descr, errbuf) < 0)
		return (-1);

#ifdef HAVE_DAG_API
	if (dag_platform_finddevs(alldevsp, errbuf) < 0)
		return (-1);
#endif /* HAVE_DAG_API */

	return (0);
}

/*
 *  Attach the given BPF code to the packet capture device.
 */
static int
pcap_setfilter_linux(pcap_t *handle, struct bpf_program *filter)
{
#ifdef SO_ATTACH_FILTER
	struct sock_fprog	fcode;
	int			can_filter_in_kernel;
	int			err = 0;
#endif

	if (!handle)
		return -1;
	if (!filter) {
	        strncpy(handle->errbuf, "setfilter: No filter specified",
			sizeof(handle->errbuf));
		return -1;
	}

	/* Make our private copy of the filter */

	if (install_bpf_program(handle, filter) < 0)
		/* install_bpf_program() filled in errbuf */
		return -1;

	/*
	 * Run user level packet filter by default. Will be overriden if
	 * installing a kernel filter succeeds.
	 */
	handle->md.use_bpf = 0;

	/* Install kernel level filter if possible */

#ifdef SO_ATTACH_FILTER
#ifdef USHRT_MAX
	if (handle->fcode.bf_len > USHRT_MAX) {
		/*
		 * fcode.len is an unsigned short for current kernel.
		 * I have yet to see BPF-Code with that much
		 * instructions but still it is possible. So for the
		 * sake of correctness I added this check.
		 */
		fprintf(stderr, "Warning: Filter too complex for kernel\n");
		fcode.filter = NULL;
		can_filter_in_kernel = 0;
	} else
#endif /* USHRT_MAX */
	{
		/*
		 * Oh joy, the Linux kernel uses struct sock_fprog instead
		 * of struct bpf_program and of course the length field is
		 * of different size. Pointed out by Sebastian
		 *
		 * Oh, and we also need to fix it up so that all "ret"
		 * instructions with non-zero operands have 65535 as the
		 * operand, and so that, if we're in cooked mode, all
		 * memory-reference instructions use special magic offsets
		 * in references to the link-layer header and assume that
		 * the link-layer payload begins at 0; "fix_program()"
		 * will do that.
		 */
		switch (fix_program(handle, &fcode)) {

		case -1:
		default:
			/*
			 * Fatal error; just quit.
			 * (The "default" case shouldn't happen; we
			 * return -1 for that reason.)
			 */
			return -1;

		case 0:
			/*
			 * The program performed checks that we can't make
			 * work in the kernel.
			 */
			can_filter_in_kernel = 0;
			break;

		case 1:
			/*
			 * We have a filter that'll work in the kernel.
			 */
			can_filter_in_kernel = 1;
			break;
		}
	}

	if (can_filter_in_kernel) {
		if ((err = set_kernel_filter(handle, &fcode)) == 0)
		{
			/* Installation succeded - using kernel filter. */
			handle->md.use_bpf = 1;
		}
		else if (err == -1)	/* Non-fatal error */
		{
			/*
			 * Print a warning if we weren't able to install
			 * the filter for a reason other than "this kernel
			 * isn't configured to support socket filters.
			 */
			if (errno != ENOPROTOOPT && errno != EOPNOTSUPP) {
				fprintf(stderr,
				    "Warning: Kernel filter failed: %s\n",
					pcap_strerror(errno));
			}
		}
	}

	/*
	 * If we're not using the kernel filter, get rid of any kernel
	 * filter that might've been there before, e.g. because the
	 * previous filter could work in the kernel, or because some other
	 * code attached a filter to the socket by some means other than
	 * calling "pcap_setfilter()".  Otherwise, the kernel filter may
	 * filter out packets that would pass the new userland filter.
	 */
	if (!handle->md.use_bpf)
		reset_kernel_filter(handle);

	/*
	 * Free up the copy of the filter that was made by "fix_program()".
	 */
	if (fcode.filter != NULL)
		free(fcode.filter);

	if (err == -2)
		/* Fatal error */
		return -1;
#endif /* SO_ATTACH_FILTER */

	return 0;
}

/*
 *  Linux uses the ARP hardware type to identify the type of an
 *  interface. pcap uses the DLT_xxx constants for this. This
 *  function takes a pointer to a "pcap_t", and an ARPHRD_xxx
 *  constant, as arguments, and sets "handle->linktype" to the
 *  appropriate DLT_XXX constant and sets "handle->offset" to
 *  the appropriate value (to make "handle->offset" plus link-layer
 *  header length be a multiple of 4, so that the link-layer payload
 *  will be aligned on a 4-byte boundary when capturing packets).
 *  (If the offset isn't set here, it'll be 0; add code as appropriate
 *  for cases where it shouldn't be 0.)
 *
 *  If "cooked_ok" is non-zero, we can use DLT_LINUX_SLL and capture
 *  in cooked mode; otherwise, we can't use cooked mode, so we have
 *  to pick some type that works in raw mode, or fail.
 *
 *  Sets the link type to -1 if unable to map the type.
 */
static void map_arphrd_to_dlt(pcap_t *handle, int arptype, int cooked_ok)
{
	switch (arptype) {

	case ARPHRD_ETHER:
	case ARPHRD_METRICOM:
	case ARPHRD_LOOPBACK:
		handle->linktype = DLT_EN10MB;
		handle->offset = 2;
		break;

	case ARPHRD_EETHER:
		handle->linktype = DLT_EN3MB;
		break;

	case ARPHRD_AX25:
		handle->linktype = DLT_AX25;
		break;

	case ARPHRD_PRONET:
		handle->linktype = DLT_PRONET;
		break;

	case ARPHRD_CHAOS:
		handle->linktype = DLT_CHAOS;
		break;

#ifndef ARPHRD_IEEE802_TR
#define ARPHRD_IEEE802_TR 800	/* From Linux 2.4 */
#endif
	case ARPHRD_IEEE802_TR:
	case ARPHRD_IEEE802:
		handle->linktype = DLT_IEEE802;
		handle->offset = 2;
		break;

	case ARPHRD_ARCNET:
		handle->linktype = DLT_ARCNET_LINUX;
		break;